datht commited on
Commit
029e500
·
verified ·
1 Parent(s): 5986405

Training in progress, epoch 1

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -1,39 +1,47 @@
1
  {
2
- "_name_or_path": "FacebookAI/xlm-roberta-base",
3
  "architectures": [
4
- "XLMRobertaForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "bos_token_id": 0,
8
  "classifier_dropout": null,
9
  "eos_token_id": 2,
 
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
- "0": "negative",
15
- "1": "neutral",
16
- "2": "positive"
 
 
 
 
17
  },
18
  "initializer_range": 0.02,
19
  "intermediate_size": 3072,
20
  "label2id": {
21
- "negative": 0,
22
- "neutral": 1,
23
- "positive": 2
 
 
 
 
24
  },
25
  "layer_norm_eps": 1e-05,
26
- "max_position_embeddings": 514,
27
- "model_type": "xlm-roberta",
28
  "num_attention_heads": 12,
29
  "num_hidden_layers": 12,
30
- "output_past": true,
31
  "pad_token_id": 1,
32
  "position_embedding_type": "absolute",
33
  "problem_type": "single_label_classification",
 
34
  "torch_dtype": "float16",
35
- "transformers_version": "4.48.0.dev0",
36
  "type_vocab_size": 1,
37
  "use_cache": true,
38
- "vocab_size": 250002
39
  }
 
1
  {
 
2
  "architectures": [
3
+ "RobertaForSequenceClassification"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "bos_token_id": 0,
7
  "classifier_dropout": null,
8
  "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
+ "0": "Anger",
15
+ "1": "Disgust",
16
+ "2": "Enjoyment",
17
+ "3": "Fear",
18
+ "4": "Other",
19
+ "5": "Sadness",
20
+ "6": "Surprise"
21
  },
22
  "initializer_range": 0.02,
23
  "intermediate_size": 3072,
24
  "label2id": {
25
+ "Anger": 0,
26
+ "Disgust": 1,
27
+ "Enjoyment": 2,
28
+ "Fear": 3,
29
+ "Other": 4,
30
+ "Sadness": 5,
31
+ "Surprise": 6
32
  },
33
  "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 258,
35
+ "model_type": "roberta",
36
  "num_attention_heads": 12,
37
  "num_hidden_layers": 12,
 
38
  "pad_token_id": 1,
39
  "position_embedding_type": "absolute",
40
  "problem_type": "single_label_classification",
41
+ "tokenizer_class": "PhobertTokenizer",
42
  "torch_dtype": "float16",
43
+ "transformers_version": "4.50.0",
44
  "type_vocab_size": 1,
45
  "use_cache": true,
46
+ "vocab_size": 64001
47
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01234f0e63a987c7bd768b5eb4a047343844de0414b14fa4f6625f88698c7771
3
- size 556116054
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3f92f4f337ce669ee4c32c92b14424fdb89d85aea6a8ac00f5afb36a7f92301
3
+ size 270031446
runs/May08_04-16-29_hn-fornix-testing-gpu-platform-2/events.out.tfevents.1746677815.hn-fornix-testing-gpu-platform-2.2355931.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a882d6c3f7db0e0699caff82f30dae7a9c9d5eff6201dea8af9627cc6599a41
3
+ size 6246
special_tokens_map.json CHANGED
@@ -2,13 +2,7 @@
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
  "pad_token": "<pad>",
13
  "sep_token": "</s>",
14
  "unk_token": "<unk>"
 
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
5
+ "mask_token": "<mask>",
 
 
 
 
 
 
6
  "pad_token": "<pad>",
7
  "sep_token": "</s>",
8
  "unk_token": "<unk>"
tokenizer_config.json CHANGED
@@ -32,9 +32,9 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "250001": {
36
  "content": "<mask>",
37
- "lstrip": true,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
@@ -53,7 +53,7 @@
53
  "padding_side": "right",
54
  "return_tensors": "pt",
55
  "sep_token": "</s>",
56
- "tokenizer_class": "XLMRobertaTokenizer",
57
  "truncation": true,
58
  "unk_token": "<unk>"
59
  }
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "64000": {
36
  "content": "<mask>",
37
+ "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
 
53
  "padding_side": "right",
54
  "return_tensors": "pt",
55
  "sep_token": "</s>",
56
+ "tokenizer_class": "PhobertTokenizer",
57
  "truncation": true,
58
  "unk_token": "<unk>"
59
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:536ce93c201df248528d59f8c971cae23d68a406f45d52f62ee954992c11c233
3
  size 6904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98531142e45f8b77fe7b0be871a47dd7dc54e06a3503719b26dcf6b8793ae55
3
  size 6904
vocab.txt ADDED
The diff for this file is too large to render. See raw diff